Awesome MCP › CLI Tools

3choff/mcp-chatbot

⭐ 251 Python added to this list on 2025-05-14 repository created 2024-12-05

MCP Chatbot is a command-line interface (CLI) chatbot designed to demonstrate the integration of the Model Context Protocol (MCP) with dynamic tool discovery and multi-server support. The project highlights MCP's flexibility by enabling compatibility with any large language model (LLM) provider that adheres to OpenAI API standards, such as Llama 3.2 90b and GPT-4o mini. The chatbot dynamically discovers tools from configured MCP servers and incorporates them into the system prompt, allowing the LLM to understand and utilize the available capabilities effectively. The architecture supports multiple MCP servers configured via a JSON file, similar to the Claude Desktop App, facilitating easy integration and environment variable management. The project is implemented in Python and requires dependencies like python-dotenv, requests, mcp, and uvicorn. The core components include Configuration for managing environment variables and server settings, Server for MCP server initialization and tool management, Tool representing individual tools, LLMClient for communication with the LLM provider, and ChatSession to orchestrate interactions between the user, LLM, and tools. The runtime flow involves loading configurations, initializing servers, discovering tools, formatting them for the LLM, and then entering a loop where user input is processed by the LLM, which decides whether to call a tool or respond directly. Tool results are sent back to the LLM for interpretation before presenting the final response to the user. This project serves as a practical example of leveraging MCP to build flexible, multi-tool chatbots that can work with various LLM providers and server setups, making it a valuable resource for developers interested in MCP and advanced chatbot architectures.

https://github.com/3choff/mcp-chatbot

chat-sessionchatbotchatsessioncli-chatbotdirect-responsedynamic-tool-discoveryenvironment-variablesgpt-4o-minijson-configurationllama-3.2llm-communicationllm-providerllm-provider-compatibilityllmclientmcpmcp-serversmit-licensemodel-context-protocolmulti-server-supportopenai-api-standardspythonserver-configurationsystem-prompttool-calltool-executiontool-formattingtool-integration

Also in CLI Tools

Hmbown/CodeWhale

An open-source terminal coding agent written in Rust, with MCP support, multi-model routing and multi-agent orchestration.

yamadashy/repomix

Repomix is a tool that packs entire code repositories into single, AI-friendly files optimized for feeding Large Language Models and other AI tools, with features for token counting, security, and customization.

QwenLM/qwen-code

Open-source terminal coding agent in TypeScript from the Qwen team that consumes MCP servers as tool providers, alongside subagents, skills, hooks, IDE plugins and support for OpenAI, Anthropic, Gemini and Qwen APIs.

1jehuang/jcode

jcode is an extremely RAM-efficient and fast AI coding agent harness for the terminal, designed to optimize multi-session workflows.

txn2/kubefwd

kubefwd is a command-line tool that bulk port forwards Kubernetes services to a local machine, enabling seamless local development by accessing cluster services with their original names and connection strings.

davepoon/buildwithclaude

A comprehensive collection of specialized AI subagents, slash commands, and MCP server integrations designed to enhance the Claude Code AI development environment with powerful automation and domain-specific expertise.

av/harbor

Harbor is a containerized toolkit that enables effortless deployment and management of local large language model backends, frontends, and services with integrated support for the Model Context Protocol ecosystem.

mattzcarey/shippie

Shippie is an AI-powered code review agent that integrates Large Language Models into CI/CD pipelines and functions as a Model Context Protocol client for enhanced integration with external tools.